easylinux/kube-prometheus
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add runbook_url annotation to all alerts

Browse Source 
Signed-off-by: ArthurSens <arthursens2005@gmail.com>
This commit is contained in:
ArthurSens
2021-03-05 12:54:03 +00:00
parent ebd4b28b91
commit e586afb280
10 changed files with 72 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
manifests/alertmanager-prometheusRule.yaml
View File

@@ -17,6 +17,7 @@ spec:
- alert: AlertmanagerFailedReload
annotations:
description: Configuration has failed to load for {{ $labels.namespace }}/{{ $labels.pod}}.
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/alertmanagerfailedreload
summary: Reloading an Alertmanager configuration has failed.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
@@ -28,6 +29,7 @@ spec:
- alert: AlertmanagerMembersInconsistent
annotations:
description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} has only found {{ $value }} members of the {{$labels.job}} cluster.
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/alertmanagermembersinconsistent
summary: A member of an Alertmanager cluster has not found all other cluster members.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
@@ -41,6 +43,7 @@ spec:
- alert: AlertmanagerFailedToSendAlerts
annotations:
description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} failed to send {{ $value | humanizePercentage }} of notifications to {{ $labels.integration }}.
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/alertmanagerfailedtosendalerts
summary: An Alertmanager instance failed to send notifications.
expr: |
(
@@ -55,6 +58,7 @@ spec:
- alert: AlertmanagerClusterFailedToSendAlerts
annotations:
description: The minimum notification failure rate to {{ $labels.integration }} sent from any instance in the {{$labels.job}} cluster is {{ $value | humanizePercentage }}.
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/alertmanagerclusterfailedtosendalerts
summary: All Alertmanager instances in a cluster failed to send notifications to a critical integration.
expr: |
min by (namespace,service, integration) (
@@ -69,6 +73,7 @@ spec:
- alert: AlertmanagerClusterFailedToSendAlerts
annotations:
description: The minimum notification failure rate to {{ $labels.integration }} sent from any instance in the {{$labels.job}} cluster is {{ $value | humanizePercentage }}.
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/alertmanagerclusterfailedtosendalerts
summary: All Alertmanager instances in a cluster failed to send notifications to a non-critical integration.
expr: |
min by (namespace,service, integration) (
@@ -83,6 +88,7 @@ spec:
- alert: AlertmanagerConfigInconsistent
annotations:
description: Alertmanager instances within the {{$labels.job}} cluster have different configurations.
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/alertmanagerconfiginconsistent
summary: Alertmanager instances within the same cluster have different configurations.
expr: |
count by (namespace,service) (
@@ -95,6 +101,7 @@ spec:
- alert: AlertmanagerClusterDown
annotations:
description: '{{ $value | humanizePercentage }} of Alertmanager instances within the {{$labels.job}} cluster have been up for less than half of the last 5m.'
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/alertmanagerclusterdown
summary: Half or more of the Alertmanager instances within the same cluster are down.
expr: |
(
@@ -113,6 +120,7 @@ spec:
- alert: AlertmanagerClusterCrashlooping
annotations:
description: '{{ $value | humanizePercentage }} of Alertmanager instances within the {{$labels.job}} cluster have restarted at least 5 times in the last 10m.'
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/alertmanagerclustercrashlooping
summary: Half or more of the Alertmanager instances within the same cluster are crashlooping.
expr: |
(